Følg
Yuki Takezawa
Yuki Takezawa
Andre navn竹澤 祐貴
Kyoto University / OIST
Verifisert e-postadresse på ml.ist.i.kyoto-u.ac.jp - Startside
Tittel
Sitert av
Sitert av
År
Fixed Support Tree-Sliced Wasserstein Barycenter
Y Takezawa, R Sato, Z Kozareva, S Ravi, M Yamada
AISTATS 2022 - International Conference on Artificial Intelligence and …, 2021
172021
Embarrassingly simple text watermarks
R Sato, Y Takezawa, H Bao, K Niwa, M Yamada
arXiv preprint arXiv:2310.08920, 2023
142023
Supervised Tree-Wasserstein Distance
Y Takezawa, R Sato, M Yamada
ICML 2021 - International Conference on Machine Learning 139, 10086-10095, 2021
142021
Necessary and Sufficient Watermark for Large Language Models
Y Takezawa, R Sato, H Bao, K Niwa, M Yamada
arXiv preprint arXiv:2310.00833, 2023
132023
Momentum tracking: Momentum acceleration for decentralized deep learning on heterogeneous data
Y Takezawa, H Bao, K Niwa, R Sato, M Yamada
TMLR 2023 - Transaction of Machine Learning Research, 2022
112022
Approximating 1-Wasserstein Distance with Trees
M Yamada, Y Takezawa, R Sato, H Bao, Z Kozareva, S Ravi
TMLR 2023 - Transaction of Machine Learning Research, 2022
102022
Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
Y Takezawa, R Sato, H Bao, K Niwa, M Yamada
NeurIPS 2023 - Advances in Neural Information Processing Systems, 2023
52023
Communication compression for decentralized learning with operator splitting methods
Y Takezawa, K Niwa, M Yamada
IEEE Transactions on Signal and Information Processing over Networks, 2023
42023
Theoretical analysis of primal-dual algorithm for non-convex stochastic decentralized optimization
Y Takezawa, K Niwa, M Yamada
arXiv preprint arXiv:2205.11979, 2022
42022
Polyak Meets Parameter-free Clipped Gradient Descent
Y Takezawa, H Bao, R Sato, K Niwa, M Yamada
NeurIPS 2024 - Advances in Neural Information Processing Systems, 2024
32024
A Localized Primal-Dual Method for Centralized/Decentralized Federated Learning Robust to Data Heterogeneity
I Tyou, T Murata, T Fukami, Y Takezawa, K Niwa
IEEE Transactions on Signal and Information Processing over Networks, 2023
22023
An Empirical Study of Self-Supervised Learning with Wasserstein Distance
M Yamada, Y Takezawa, G Houry, KM Düsterwald, D Sulem, H Zhao, ...
Entropy 2024, 2024
1*2024
PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis
S Ishikawa, M Yamada, H Bao, Y Takezawa
arXiv preprint arXiv:2405.14650, 2024
12024
Large-scale similarity search with Optimal Transport
C Laouar, Y Takezawa, M Yamada
EMNLP 2023 - Empirical Methods in Natural Language Processing, 2023
12023
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
K Shinoda, Y Takezawa, M Suzuki, Y Iwasawa, Y Matsuo
MMM 2023 - International Conference on Multimedia Modeling, 2023
2023
Parameter-free Clipped Gradient Descent Meets Polyak
Y Takezawa, H Bao, R Sato, K Niwa, M Yamada
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 0
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–16